On the Expressivity of Markov Reward.
David AbelWill DabneyAnna HarutyunyanMark K. HoMichael L. LittmanDoina PrecupSatinder SinghPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- markov chain
- semi markov
- markov model
- conditional independence
- long run
- bandit problems
- genetic algorithm
- website
- markov processes
- markov process
- computational properties
- directed acyclic graph
- average reward
- reward function
- data sets
- evolutionary algorithm
- relational databases
- computational complexity
- database systems
- three dimensional
- real world